• Title/Summary/Keyword: 안면 얼굴 영상

Search Result 39, Processing Time 0.019 seconds

A Study on the Correlationship Analysis Between Big 5 Model Types and Face Feature for Interview System Application - Focusing on Men in the 20's (면접 시스템 적용을 위한 5대 성격 유형과 얼굴 특징간의 상관관계 분석 연구 : 20대 남성을 대상으로)

  • Kim, Bong-Hyun;Cho, Dong-Uk
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.36 no.2B
    • /
    • pp.168-175
    • /
    • 2011
  • In modem society, human relationships has been received much attention as important element to judge the success as well as the social life of the individual. To respond to these changing times has been used various ways to maintain an appropriate relationship that each other's character can be predicted. In this paper, we should be carried out a study on correlation analysis and features of five-character types to extract shape of philtrum, mouth, ears in facial image of Men in the 20's for Interview system application. From this, we extracted to area of philtrum, mouth, ears by Visual C++ to face and side image. Then we performed analysis, comparison a group of S-character types to find a result according to philtrum rate, mouth size, shape of ears. As a result, we drew a significance through morphological results by philtrum rate, mouth size, shape of ears as five-character types.

Development of Smart-Car Safety Management System Focused on Drunk Driving Control (음주제어를 중심으로 한 스마트 자동차 안전 관리 시스템 개발)

  • Lee, Se-Hwan;Cho, Dong-Uk
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.37 no.7C
    • /
    • pp.565-575
    • /
    • 2012
  • In the modern everyday life, cars the largest proportion of smart features that require mounting in a variety of smart devices and smart methods on have been developed. In this paper, the smart car among the main core of the safety management system optional for the control of drinking and drowsiness, as part of system development, will be drinking if you start your car automatically is to develop a system to avoid driving. For this, through image processing to analyze the driver's seat of the driver's facial color how to determine whether or not drinking alcohol is proposed. In particular, the system developed in this paper determines whether or not drinking alcohol before the face images without the need for alcohol after only a unique color change of the face appears to target only way to determine whether drinking and actual alcohol control center of a smart car safety control management system can be applied effectively. The experiment was done in 30 patients after drinking appears face color changes of them. We also perform an analysis on the statistical significance of the experimental results to verify the effectiveness of the proposed method.

Face Regions Segmentation and Five Sensory Organs & Myeongdang Extraction Method for Baby Ocular Inspection (소아 망진을 위한 얼굴 영역 분할과 오관 및 명당 추출 방법)

  • Kim Bong-Hyun;Lee Se-Hwan;Kim Seung-Youn;Lee Bok-Gi;Koo Kyung-Ok;Cho Dong-Uk
    • The Journal of the Korea Contents Association
    • /
    • v.6 no.4
    • /
    • pp.69-80
    • /
    • 2006
  • Interest about baby health increased into promise of all life health on society. Prevention disease or treatment about baby health is important, but it is important that first of grasping baby state through correct diagnosis. In this paper, diagnosis method for baby ocular inspection of Oriental medicine applying image processing technology is presented. For this, extracting baby frontal face image based on skin color, five sensory organs extraction and extraction of myeongdang based on position information is proposed. Finally, usefulness of method Proposed by an experiment world prove.

  • PDF

Front Face Image Analysis of Twentities Generation Man for Sasang Constitution Classification (20대 남성의 사상체질 분류를 위한 상안부의 얼굴 요소 분석)

  • Park, Sun-Ae;Lee, Se-Hwan;Kim, Bong-Hyun;Ka, Min-Kyoung;Cho, Dong-Uk
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2007.11a
    • /
    • pp.90-93
    • /
    • 2007
  • 우리나라만의 독창적인 의료체계인 사상체질은 의학적 본질의 우수성에도 불구하고 크게 대중화 되지 않았으며 인지도 또한 높지 못하다. 이는 사상체질에서 가장 중요한 부분이 사상체질의 정확한 분류인데 현재 임상현장에서 행해지고 있는 사상체질 분류 방식은 임상의의 경험과 주관적 소견에 의해 분류되고 있기 때문에 진단 결과에 객관성이 없고 정확도가 낮게 평가되고 있는 실정이다. 이를 위해 사상체질 진단 방법 중 하나인 용모사기론을 IT공학의 영상처리에 적용하여 안면 영상 분석을 통해 사상체질 분류를 수행하고자 한다. 이를 위해 본 논문에서는 사상의학적 원전과 기존의 방법들을 조사, 연구하여 사상체질 분류의 중요한 요소를 결정하고 시스템 구현을 목표로 실험을 통해 사상체질 분류의 유의성을 갖는 측정 요소에 대해 검증해 보고자 한다.

Influence of the angles and number of scans on the accuracy of 3D laser scanning (3 차원 레이저 스캔영상 채득 시 스캔각도와 횟수에 따른 정확도)

  • Lee, Kyung-Min;Song, Hyo-Young;Lee, Ki-Heon;Hwang, Hyeon-Shik
    • The korean journal of orthodontics
    • /
    • v.41 no.2
    • /
    • pp.76-86
    • /
    • 2011
  • Objective: To investigate whether the accuracy of 3D laser scanning is influenced by the angles and number of scans. Methods: Using a 3D laser scanner, 10 manikins with facial markers were scanned at 7 horizontal angles (front view and at $20^{\circ}$, $45^{\circ}$, and $60^{\circ}$ angles on the right and left sides). Three-dimensional facial images were reconstructed by 6 methods differing in the number and angles of scans, and measurements of these images were compared to the physical measurements from the manikins. Results: The laser scan images were magnified by 0.14 - 0.26%. For images reconstructed by merging 2 scans, excluding the front view; and by merging 3 scans, including the front view and scans obtained at $20^{\circ}$ on both sides; several measurements were significantly different than the physical measurements. However, for images reconstructed by merging 3 scans, including the front view; and 5 scans, including the front view and scans obtained at $20^{\circ}$ and $60^{\circ}$ on both sides; only 1 measurement was significantly different. Conclusions: These results suggest that the number and angle of scans influence the accuracy of 3D laser scanning. A minimum of 3 scans, including the front view and scans obtained at more than $45^{\circ}$ on both sides, should be integrated to obtain accurate 3D facial images.

Exploration of deep learning facial motions recognition technology in college students' mental health (딥러닝의 얼굴 정서 식별 기술 활용-대학생의 심리 건강을 중심으로)

  • Li, Bo;Cho, Kyung-Duk
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.3
    • /
    • pp.333-340
    • /
    • 2022
  • The COVID-19 has made everyone anxious and people need to keep their distance. It is necessary to conduct collective assessment and screening of college students' mental health in the opening season of every year. This study uses and trains a multi-layer perceptron neural network model for deep learning to identify facial emotions. After the training, real pictures and videos were input for face detection. After detecting the positions of faces in the samples, emotions were classified, and the predicted emotional results of the samples were sent back and displayed on the pictures. The results show that the accuracy is 93.2% in the test set and 95.57% in practice. The recognition rate of Anger is 95%, Disgust is 97%, Happiness is 96%, Fear is 96%, Sadness is 97%, Surprise is 95%, Neutral is 93%, such efficient emotion recognition can provide objective data support for capturing negative. Deep learning emotion recognition system can cooperate with traditional psychological activities to provide more dimensions of psychological indicators for health.

Basic Study on the Image Instrument of the Facial-form by the 3D-facial Scanner (얼굴스캐너를 활용한 안면형상 영상진단기의 기초 연구)

  • Kim, Gyeong-Cheol;Lee, Jeong-Won;Kim, Hoon;Shin, Soon-Shik;Lee, Hai-Woong;Lee, Yong-Tae;Chi, Gyoo-Yong;Kim, Jong-Won
    • Journal of Physiology & Pathology in Korean Medicine
    • /
    • v.22 no.2
    • /
    • pp.497-501
    • /
    • 2008
  • 3D facial scanner for an accurate analysis is measured precisely a distance in straight, a distance in curved line, an angle in 3D data, the area of surface. We can easy acquire 3D data by the method of 0.8sec in each scan with easy handling, simple merge to whole face, harmless and fast process. In the HyungSang medicine, the inspection of the facial shape includes the Dam(gall bladder) - Bang Kwang(urinary bladder) body, the Jung${\cdot}$Gi${\cdot}$Shin${\cdot}$Hyul, the six merdian types etc. And we will collect the evidence based date verifing in the HyungSang clinical medicine. As we will analyze the facial whole form and the size${\cdot}$length${\cdot}$angle of the facial part, put the facial form's standardization on a solid foundation.

A Study of the Development of a Korea Wind Chill Temperature Index (II) - A Preliminary Study of the Development of the Korea Wind Chill Temperature Index - (한국형 체감온도지수 개발연구(II) - 체감온도지수 개발을 위한 예비실험 -)

  • Park, Jong-Kil;Jung, Woo-Sik;Kim, Byung-Soo;Yoon, Sook-Hee;Lee, Jong-Tae;Nam, Jae-Cheol;Ryoo, Sang-Boom;Kim, Eun-Byul;Park, Gil-Un;Song, Jeong-Hui
    • Journal of the Korean earth science society
    • /
    • v.28 no.7
    • /
    • pp.891-902
    • /
    • 2007
  • This paper aims to develop a Korea wind chill temperature index using an experimental method. For this, the researchers carried out a preliminary experiment in order to of for provisions necessary for the selection and safety of test participants, accuracy of experiment, and readiness for various situations that may occur during experiment. The researchers also investigated test subjects' safety and experiment conditions in which wind speed changes from calm condition into strong wind speed condition under the constant air temperature of $5^{\circ}C$. The results of this study are as follows. With regard to the variation of facial skin temperature such as forehead, cheek, nose, and chin, the skin temperature of cheek closely appears to depend on the change of air temperature and wind speed, exhibit a stable variation trend of skin temperature, and indicate the lowest temperature than any other facial parts. The skin temperature of women tends to be more sensitive than that of man and the skin temperature of human tends to decrease at weak wind speed under constant air temperature. It was also found that it is not necessary to take the influence of standard wind speed into consideration when a wind chill index is developed.

Research on Generative AI for Korean Multi-Modal Montage App (한국형 멀티모달 몽타주 앱을 위한 생성형 AI 연구)

  • Lim, Jeounghyun;Cha, Kyung-Ae;Koh, Jaepil;Hong, Won-Kee
    • Journal of Service Research and Studies
    • /
    • v.14 no.1
    • /
    • pp.13-26
    • /
    • 2024
  • Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.